| { |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "GPT2Model" |
| ], |
| "attn_pdrop": 0.1, |
| "bos_token_id": 0, |
| "embd_pdrop": 0.1, |
| "eos_token_id": 0, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "gpt2", |
| "n_ctx": 1024, |
| "n_embd": 1024, |
| "n_head": 16, |
| "n_inner": null, |
| "n_layer": 24, |
| "n_positions": 1024, |
| "n_special": 0, |
| "pad_token_id": 0, |
| "predict_special_tokens": true, |
| "quantization_config": { |
| "modules_to_not_convert": null, |
| "quant_method": "torchao", |
| "quant_type": { |
| "default": { |
| "_data": { |
| "act_mapping_type": { |
| "_data": "SYMMETRIC", |
| "_type": "MappingType" |
| }, |
| "layout": { |
| "_data": {}, |
| "_type": "PlainLayout", |
| "_version": 1 |
| }, |
| "set_inductor_config": true, |
| "weight_only_decode": false |
| }, |
| "_type": "Int8DynamicActivationInt8WeightConfig", |
| "_version": 1 |
| } |
| }, |
| "quant_type_kwargs": {} |
| }, |
| "reorder_and_upcast_attn": false, |
| "resid_pdrop": 0.1, |
| "scale_attn_by_inverse_layer_idx": false, |
| "scale_attn_weights": true, |
| "summary_activation": null, |
| "summary_first_dropout": 0.1, |
| "summary_proj_to_labels": true, |
| "summary_type": "cls_index", |
| "summary_use_proj": true, |
| "task_specific_params": { |
| "text-generation": { |
| "bos_token_id": 0, |
| "do_sample": true, |
| "eos_token_id": 50257, |
| "max_length": 256, |
| "pad_token_id": 0, |
| "repetition_penalty": 1.1, |
| "temperature": 0.3, |
| "top_p": 0.9 |
| } |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "vocab_size": 50258 |
| } |
|
|
